SYNTOLOGY HomeExplorerAtlasCodeMethodologyAboutDevelopersFeedPricing
Paper · 2207.03578 · 2022

Code Translation with Compiler Representations

arXiv · PDF · Open in the Atlas

Code that ran

5 of 6 samples (functions and classes) lifted from this paper's linked repositories executed on a synthesized input in Syntology's jail (0 of them constructed an object rather than computing a result; 0 honoured the contract we drafted, 0 violated it and 4 have no contract verdict; 1 failure of our instrument; 1 no recorded run), measured 2026-11-22; repository links from the Papers with Code archive attributed under CC BY-SA, no affiliation; bodies inline only under a permissive licence as GitHub detects it. Not a reproduction of the paper's results.

"Ran" means the function executed on a synthesized input and returned a value. It is not a reproduction of the paper's results. This record, dated, as JSON: /api/ran/2207.03578.json · badge: /api/ran/2207.03578.svg

Each repository's role is a label: a classifier's output recorded on the link, or, where no role is recorded, what the Papers with Code archive marked. The line under it names its basis. Neither says who wrote the code.

RepositoryRoleRan
facebookresearch/CodeGen canonical (classifier label)
classifier basis not recorded on the link
5 ran · 1 no recorded run
FunctionStatusWhere it lives
clean_err_output Ran
ran on a synthesized input
facebookresearch/CodeGen/codegen_sources/code_runners/utils.py
pointer only (licence: MIT) · get_code("bed57f6001f65a3e")
How it ran

The body of this sample is withheld: MIT, as GitHub detects it on this paper's repository, facebookresearch/CodeGen, is in the permissive set, but a licence decision keeps the body a pointer: the reason for that decision is not recorded with it. The setup block that called it is withheld with it, because it is written against that body. source_path and origin say where the code lives, to read under the repository's own terms. A run is recorded.

extract_dict Ran
ran on a synthesized input
facebookresearch/CodeGen/codegen_sources/dataloaders/utils.py
pointer only (licence: MIT) · get_code("a985bcb5f48a99e5")
How it ran

The body of this sample is withheld: MIT, as GitHub detects it on this paper's repository, facebookresearch/CodeGen, is in the permissive set, but a licence decision keeps the body a pointer: the reason for that decision is not recorded with it. The setup block that called it is withheld with it, because it is written against that body. source_path and origin say where the code lives, to read under the repository's own terms. A run is recorded.

limit_virtual_memory Ran
ran on a synthesized input
facebookresearch/CodeGen/codegen_sources/code_runners/utils.py
pointer only (licence: MIT) · get_code("e0ec2aae48ea0c51")
How it ran

The body of this sample is withheld: MIT, as GitHub detects it on this paper's repository, facebookresearch/CodeGen, is in the permissive set, but a licence decision keeps the body a pointer: the reason for that decision is not recorded with it. The setup block that called it is withheld with it, because it is written against that body. source_path and origin say where the code lives, to read under the repository's own terms. A run is recorded.

split_python_code Ran
ran on a synthesized input
facebookresearch/CodeGen/codegen_sources/dataloaders/utils.py
pointer only (licence: MIT) · get_code("bc7150313b7bed0d")
How it ran

The body of this sample is withheld: MIT, as GitHub detects it on this paper's repository, facebookresearch/CodeGen, is in the permissive set, but a licence decision keeps the body a pointer: the reason for that decision is not recorded with it. The setup block that called it is withheld with it, because it is written against that body. source_path and origin say where the code lives, to read under the repository's own terms. A run is recorded.

timeout Ran
ran; our contract draft was wrong, not the code
facebookresearch/CodeGen/codegen_sources/IR_tools/utils_ir.py
pointer only (licence: MIT) · get_code("781797e5f4a5b6ec")
How it ran

The body of this sample is withheld: MIT, as GitHub detects it on this paper's repository, facebookresearch/CodeGen, is in the permissive set, but a licence decision keeps the body a pointer: the reason for that decision is not recorded with it. The setup block that called it is withheld with it, because it is written against that body. source_path and origin say where the code lives, to read under the repository's own terms. A run is recorded.

demangle_names_cpp Not yet run
unverified (harvested, no recorded run)
facebookresearch/CodeGen/codegen_sources/IR_tools/utils_ir.py
pointer only (licence: MIT) · get_code("eebe99a6c4082bca")
How it ran

The body of this sample is withheld: MIT, as GitHub detects it on this paper's repository, facebookresearch/CodeGen, is in the permissive set, but a licence decision keeps the body a pointer: the reason for that decision is not recorded with it. The setup block that called it is withheld with it, because it is written against that body. source_path and origin say where the code lives, to read under the repository's own terms. No invocation recorded.

Also present in other papers' code

Of 6 samples lifted from this paper's linked repositories, 6 carry a function identity and 0 do not. Of the 6 distinct functions with an identity, 2 are also present in other papers whose code we hold (1 with at least one paper dated earlier, 0 the same month, 2 later) and 4 are only here among the 52,977 papers whose code Syntology holds (as of 2026-09-26).

Only here means: among the 52,977 papers whose code Syntology holds (51,887 with lifted samples, 1,090 through their assemblies only), as of 2026-09-26, no other paper's lifted samples or current assembly bricks contain an identical function body after normalisation.

FunctionAlso present inEarliest-datedOthers named
timeout 3 other papers
1 dated earlier, 2 later
2110.03501 (2021-10)
Pretrained Language Models are Symbolic Mathematics Solvers too!
2411.00566 (2024-11)
PatternBoost: Constructions in Mathematics with a Little Help from AI
2602.07800 (2026-02)
Approximating Matrix Functions with Deep Neural Networks and Transformers
limit_virtual_memory 1 other paper
1 later
2503.07358 (2025-03)
RepoST: Scalable Repository-Level Coding Environment Construction with Sandbox Testing

Presence, not direction: an identical function body in two papers' repositories does not say who wrote it, which came from which, or that either paper's method rests on it. Matching is exact after normalisation, so a renamed or edited function is not matched. Dates are when papers appeared, not when code was written. Only .py files the harvester lifted are covered; notebooks are not read. A new-style arXiv id YYMM.NNNN dates a paper to the month 20YY-MM; otherwise Paper.year dates it to the year; otherwise it is undated. Dates are when the paper appeared, not when the code was written. Read 2026-11-22.

Repositories linked to this paper

Some links come from the archived Papers with Code dataset (CC BY-SA 4.0): attribution and licence.

Abstract

In this paper, we leverage low-level compiler intermediate representations (IR) to improve code translation. Traditional transpilers rely on syntactic information and handcrafted rules, which limits their applicability and produces unnatural-looking code. Applying neural machine translation (NMT) approaches to code has successfully broadened the set of programs on which one can get a natural-looking translation. However, they treat the code as sequences of text tokens, and still do not differentiate well enough between similar pieces of code which have different semantics in different languages. The consequence is low quality translation, reducing the practicality of NMT, and stressing the need for an approach significantly increasing its accuracy. Here we propose to augment code translation with IRs, specifically LLVM IR, with results on the C++, Java, Rust, and Go languages. Our method improves upon the state of the art for unsupervised code translation, increasing the number of correct translations by 11% on average, and up to 79% for the Java -> Rust pair with greedy decoding. We extend previous test sets for code translation, by adding hundreds of Go and Rust functions. Additionally, we train models with high performance on the problem of IR decompilation, generating programming source code from IR, and study using IRs as intermediary pivot for translation.

For agents

The same record, over MCP at https://syntology.ai/mcp:

get_harvested_code_for_paper("2207.03578")
get_code_for_paper("2207.03578")
have("2207.03578")

The run record, dated, one paper per request, free:

curl https://syntology.ai/api/ran/2207.03578.json

A badge for a README (the split and the date, never a ratio):

[![Syntology run record](https://syntology.ai/api/ran/2207.03578.svg)](https://syntology.ai/paper/2207.03578)

Connect an agent — have() is free.